{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6352548599243164, "min": 1.5858198404312134, "max": 1.8710861206054688, "count": 376 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32600.44140625, "min": 26645.12109375, "max": 40594.4296875, "count": 376 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.144329896907216, "min": 39.395161290322584, "max": 72.3529411764706, "count": 376 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19456.0, "min": 13776.0, "max": 20848.0, "count": 376 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.888870935971, "min": 1589.7784550849465, "max": 1643.6332130258231, "count": 376 }, "SoccerTwos.Self-play.ELO.sum": { "value": 310960.4409615784, "min": 217664.007909227, "max": 410588.5659338291, "count": 376 }, "SoccerTwos.Step.mean": { "value": 9999742.0, "min": 6249998.0, "max": 9999742.0, "count": 376 }, "SoccerTwos.Step.sum": { "value": 9999742.0, "min": 6249998.0, "max": 9999742.0, "count": 376 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06604859232902527, "min": -0.10717771202325821, "max": 0.08588841557502747, "count": 376 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.879475593566895, "min": -20.899654388427734, "max": 21.27772331237793, "count": 376 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06388282030820847, "min": -0.10746608674526215, "max": 0.08911468833684921, "count": 376 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -12.457149505615234, "min": -20.955886840820312, "max": 22.10044288635254, "count": 376 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 376 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 376 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.026838973852304313, "min": -0.2997705258821186, "max": 0.20987659661059685, "count": 376 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.233599901199341, "min": -56.95639991760254, "max": 40.03939998149872, "count": 376 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.026838973852304313, "min": -0.2997705258821186, "max": 0.20987659661059685, "count": 376 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.233599901199341, "min": -56.95639991760254, "max": 40.03939998149872, "count": 376 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 376 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 376 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016824819935330502, "min": 0.010986334524932317, "max": 0.022639802926278207, "count": 182 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016824819935330502, "min": 0.010986334524932317, "max": 0.022639802926278207, "count": 182 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1037929154932499, "min": 0.0973580169181029, "max": 0.13210416510701178, "count": 182 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1037929154932499, "min": 0.0973580169181029, "max": 0.13210416510701178, "count": 182 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10495370825131735, "min": 0.09941927989323934, "max": 0.13449397459626197, "count": 182 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10495370825131735, "min": 0.09941927989323934, "max": 0.13449397459626197, "count": 182 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 182 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 182 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 182 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 182 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 182 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 182 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675368422", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/swayam/miniconda3/envs/aivsai/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1675389355" }, "total": 20933.09908675, "count": 1, "self": 0.2547062500016182, "children": { "run_training.setup": { "total": 0.018279332999999953, "count": 1, "self": 0.018279332999999953 }, "TrainerController.start_learning": { "total": 20932.826101167, "count": 1, "self": 3.9952369969541905, "children": { "TrainerController._reset_env": { "total": 3.0492747479994047, "count": 20, "self": 3.0492747479994047 }, "TrainerController.advance": { "total": 20925.66328925605, "count": 264705, "self": 3.487712746646139, "children": { "env_step": { "total": 16740.51882920255, "count": 264705, "self": 16159.525152573467, "children": { "SubprocessEnvManager._take_step": { "total": 578.3572410770118, "count": 264705, "self": 15.895055308947349, "children": { "TorchPolicy.evaluate": { "total": 562.4621857680645, "count": 470956, "self": 562.4621857680645 } } }, "workers": { "total": 2.6364355520686753, "count": 264705, "self": 0.0, "children": { "worker_root": { "total": 20923.958696107245, "count": 264705, "is_parallel": true, "self": 5269.333188276369, "children": { "steps_from_proto": { "total": 0.048249625000226226, "count": 40, "is_parallel": true, "self": 0.005078376988491007, "children": { "_process_rank_one_or_two_observation": { "total": 0.04317124801173522, "count": 160, "is_parallel": true, "self": 0.04317124801173522 } } }, "UnityEnvironment.step": { "total": 15654.577258205876, "count": 264705, "is_parallel": true, "self": 42.89317328836478, "children": { "UnityEnvironment._generate_step_input": { "total": 280.45364911746367, "count": 264705, "is_parallel": true, "self": 280.45364911746367 }, "communicator.exchange": { "total": 14708.78579793911, "count": 264705, "is_parallel": true, "self": 14708.78579793911 }, "steps_from_proto": { "total": 622.4446378609377, "count": 529410, "is_parallel": true, "self": 65.03145552253682, "children": { "_process_rank_one_or_two_observation": { "total": 557.4131823384009, "count": 2117640, "is_parallel": true, "self": 557.4131823384009 } } } } } } } } } } }, "trainer_advance": { "total": 4181.656747306854, "count": 264705, "self": 25.074067883005227, "children": { "process_trajectory": { "total": 1009.6312764168599, "count": 264705, "self": 1008.656022584857, "children": { "RLTrainer._checkpoint": { "total": 0.9752538320028634, "count": 8, "self": 0.9752538320028634 } } }, "_update_policy": { "total": 3146.9514030069895, "count": 182, "self": 470.07831389695184, "children": { "TorchPOCAOptimizer.update": { "total": 2676.8730891100377, "count": 5460, "self": 2676.8730891100377 } } } } } } }, "trainer_threads": { "total": 6.250011210795492e-07, "count": 1, "self": 6.250011210795492e-07 }, "TrainerController._save_models": { "total": 0.11829954099812312, "count": 1, "self": 0.0010015820007538423, "children": { "RLTrainer._checkpoint": { "total": 0.11729795899736928, "count": 1, "self": 0.11729795899736928 } } } } } } }